There is a growing interest in leveraging multiple large language models (LLMs) for automated code optimization. However, industrial platforms deploying multiple LLMs face a critical challenge: prompts optimized for one LLM often fail with others, requiring expensive model-specific prompt engineering. This cross-model prompt engineering bottleneck severely limits the practical deployment of multi-LLM systems in production environments. We introduce Meta-Prompted Code Optimization (Mpco), a framework that automatically generates high-quality, task-specific prompts across diverse LLMs while maintaining industrial efficiency requirements. Mpco leverages meta-prompting to dynamically synthesize context-aware optimization prompts by integrating project metadata, task requirements, and LLM-specific contexts. It is an essential part of the ARTEMIS code optimization platform for automated validation and scaling.Our comprehensive evaluation on five real-world codebases with 366 hours of runtime benchmarking demonstrates Mpco’s effectiveness: it achieves overall performance improvements up to 19.06% with the best statistical rank across all systems compared to baseline methods. Analysis shows that 96% of the top-performing optimizations stem from meaningful edits. Through systematic ablation studies and meta-prompter sensitivity analysis, we identify that comprehensive context integration is essential for effective meta-prompting and that major LLMs can serve effectively as meta-prompters, providing actionable insights for industrial practitioners.

Developers relax restrictions on a type to reuse methods with other types. While type casts are prevalent, in weakly typed languages such as C++, they are also extremely permissive. Assignments where a source expression is cast into a new type and assigned to a target variable of the new type, can lead to software bugs if performed without care. In this paper, we propose an information-theoretic approach to identify poor implementations of explicit cast operations. Our approach measures accord between the source expression and the target variable using conditional entropy. We collect casts from 34 components of the Chromium project, which collectively account for 27MLOC and random-uniformly sample this dataset to create a manually labelled dataset of 271 casts. Information-theoretic vetting of these 271 casts achieves a peak precision of 81% and a recall of 90%. We additionally present the findings of an in-depth investigation of notable explicit casts, two of which were fixed in recent releases of the Chromium project.

Software developers sometimes use inefficient data structures or library interfaces without considering the potential impact they may have during the runtime of a program. This is due to the significant effort required to research and evaluate possibly more efficient alternatives. Consequently, there is a need for tooling to automate the design space exploration. Our proposed code optimisation solution, called Artemis++, tries to address this issue with automatic exploration and transformation of data structures to optimise software performance. In preliminary testing on three mainstream C++ libraries, we have observed improvements up to 16.09%, 27.90%, and 2.74% for CPU usage, runtime and memory, respectively.